CN116318549A - Message distribution method, device, computer equipment, storage medium and product - Google Patents
Message distribution method, device, computer equipment, storage medium and product Download PDFInfo
- Publication number
- CN116318549A CN116318549A CN202310268123.2A CN202310268123A CN116318549A CN 116318549 A CN116318549 A CN 116318549A CN 202310268123 A CN202310268123 A CN 202310268123A CN 116318549 A CN116318549 A CN 116318549A
- Authority
- CN
- China
- Prior art keywords
- message
- information
- receiving end
- interference
- distributed
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L1/00—Arrangements for detecting or preventing errors in the information received
- H04L1/0001—Systems modifying transmission characteristics according to link quality, e.g. power backoff
- H04L1/0033—Systems modifying transmission characteristics according to link quality, e.g. power backoff arrangements specific to the transmitter
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L1/00—Arrangements for detecting or preventing errors in the information received
- H04L1/0001—Systems modifying transmission characteristics according to link quality, e.g. power backoff
- H04L1/0036—Systems modifying transmission characteristics according to link quality, e.g. power backoff arrangements specific to the receiver
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/04—Network architectures or network communication protocols for network security for providing a confidential data exchange among entities communicating through data packet networks
- H04L63/0428—Network architectures or network communication protocols for network security for providing a confidential data exchange among entities communicating through data packet networks wherein the data content is protected, e.g. by encrypting or encapsulating the payload
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L69/00—Network arrangements, protocols or services independent of the application payload and not provided for in the other groups of this subclass
- H04L69/06—Notations for structuring of protocol data, e.g. abstract syntax notation one [ASN.1]
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Computer Security & Cryptography (AREA)
- Quality & Reliability (AREA)
- Computer Hardware Design (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The application relates to a message distribution method, a device, a computer device, a storage medium and a computer program product, relates to the technical field of computers, can be used in the financial science and technology field or other related fields, and can improve the message distribution efficiency. The method comprises the following steps: a receiving message sending end sends a message to be distributed to a message distributing end; acquiring a plurality of message information in the message to be distributed, removing interference message information in the message information, and acquiring target message information based on the removed residual message information; the interference message information is message information with the association degree with the message receiving end smaller than a preset threshold value; inputting the target message information into a trained message sorting model, and determining a target message receiving end corresponding to the message to be distributed by the message sorting model based on the target message information; and sending the message to be distributed to the target message receiving end.
Description
Technical Field
The present invention relates to the field of computer technologies, and in particular, to a method, an apparatus, a computer device, a storage medium, and a computer program product for distributing a message.
Background
With the development of computer technology, in order to improve the message interaction efficiency between financial institutions in different areas, service sites of the financial institutions can realize information interaction with service sites in different areas by adding globalized message service institutions. In order to improve service use efficiency, the financial institution may only select a part of service nodes to join in the message service institution, and for each sub-service node subordinate to the service node, the service node may distribute the received multiple messages to the corresponding sub-service node or.
In the related art, after a service website receives a message sent by a message mechanism, the service website can distribute the message containing one or more keywords to corresponding sub-service websites according to a keyword matching rule table which is maintained by service staff according to experience.
However, the above manner is completely dependent on the maintenance of the keyword matching rule table, so that a large number of messages are difficult to determine corresponding sub-service network points through the keyword matching rule table, and manual sorting is required; at the same time, business personnel also need to spend a great deal of time maintaining. As can be seen, the related art still has the problem of low message distribution efficiency.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a message distribution method, apparatus, computer device, computer readable storage medium, and computer program product that can improve the efficiency of message distribution.
In a first aspect, the present application provides a method for distributing a message, where the method includes:
a receiving message sending end sends a message to be distributed to a message distributing end;
acquiring a plurality of message information in the message to be distributed, removing interference message information in the message information, and acquiring target message information based on the removed residual message information; the interference message information is message information with the association degree with the message receiving end smaller than a preset threshold value;
inputting the target message information into a trained message sorting model, and determining a target message receiving end corresponding to the message to be distributed by the message sorting model based on the target message information;
and sending the message to be distributed to the target message receiving end.
In one embodiment, before the removing the interference message information in the plurality of message information, the method further includes:
acquiring a service type of the message to be distributed and a plurality of service elements associated with the service type;
Determining interference business elements of which the association degree with a message receiving end is smaller than a preset threshold value in the business elements;
and determining the interference message information in the message information according to the interference service element.
In one embodiment, the determining, of the plurality of service elements, an interference service element having a degree of association with the message receiving end smaller than a preset threshold value includes:
acquiring a pre-stored configuration table; the configuration table is recorded with a plurality of candidate business elements, and the association degree between each candidate business element and the message receiving end is smaller than a preset threshold value;
and determining interference business elements in the business elements based on the matching result of the business elements and each candidate business element in the configuration table.
In one embodiment, before the removing the interference message information in the plurality of message information, the method further includes:
acquiring a plurality of message blocks of the message to be distributed; the message blocks correspond to different topics;
determining an interference message block in the message blocks, and determining message information in the interference message block as interference message information; and the association degree between the subject of the interference message block and the message receiving end is smaller than a preset threshold value.
In one embodiment, before the message to be distributed, which is sent by the receiving message sending end to the message distributing end, the method further includes:
receiving messages uploaded by a plurality of message receiving terminals;
encrypting the messages uploaded by the message receiving ends based on a preset appointed encryption key to obtain an encrypted message set; the agreed encryption key is an encryption key agreed in advance between the message distribution terminal and the message transmission terminal;
and sending the encrypted message set to the message sending end so as to trigger the message sending end to return a plurality of messages to be distributed to the message distributing end according to the messages in the encrypted message set.
In one embodiment, the encrypting the messages uploaded by the multiple message receiving ends based on the preset agreed encryption key to obtain an encrypted message set includes:
encrypting the message uploaded by each message receiving end based on the encryption key corresponding to each message receiving end to obtain a plurality of encrypted messages;
encrypting the plurality of encrypted messages based on a preset appointed encryption key to obtain an encrypted message set.
In one embodiment, the message sorting model is obtained through training by the following steps:
for each message uploaded by the message receiving terminals, rejecting the interference message information in each message to obtain a plurality of sample messages;
determining a receiving end label of each sample message based on the message receiving end corresponding to each message;
training a text classification model based on the plurality of sample messages and the receiving end labels of each sample message in the plurality of sample messages, and obtaining the trained message sorting model under the condition that training ending conditions are met.
In a second aspect, the present application further provides a packet distribution apparatus, where the apparatus includes:
the message receiving module is used for receiving a message to be distributed, which is sent to the message distribution terminal by the message sending terminal;
the interference message information eliminating module is used for acquiring a plurality of message information in the message to be distributed, eliminating the interference message information in the message information and obtaining target message information based on the residual message information after elimination; the interference message information is message information with the association degree with the message receiving end smaller than a preset threshold value;
The sorting module is used for inputting the target message information into a trained message sorting model, and determining a target message receiving end corresponding to the message to be distributed based on the target message information by the message sorting model;
and the message forwarding module is used for sending the message to be distributed to the target message receiving end.
In a third aspect, the present application also provides a computer device. The computer device comprises a memory storing a computer program and a processor which when executing the computer program performs the steps of:
a receiving message sending end sends a message to be distributed to a message distributing end;
acquiring a plurality of message information in the message to be distributed, removing interference message information in the message information, and acquiring target message information based on the removed residual message information; the interference message information is message information with the association degree with the message receiving end smaller than a preset threshold value;
inputting the target message information into a trained message sorting model, and determining a target message receiving end corresponding to the message to be distributed by the message sorting model based on the target message information;
And sending the message to be distributed to the target message receiving end.
In a fourth aspect, the present application also provides a computer-readable storage medium. The computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:
a receiving message sending end sends a message to be distributed to a message distributing end;
acquiring a plurality of message information in the message to be distributed, removing interference message information in the message information, and acquiring target message information based on the removed residual message information; the interference message information is message information with the association degree with the message receiving end smaller than a preset threshold value;
inputting the target message information into a trained message sorting model, and determining a target message receiving end corresponding to the message to be distributed by the message sorting model based on the target message information;
and sending the message to be distributed to the target message receiving end.
In a fifth aspect, the present application also provides a computer program product. The computer program product comprises a computer program which, when executed by a processor, implements the steps of:
A receiving message sending end sends a message to be distributed to a message distributing end;
acquiring a plurality of message information in the message to be distributed, removing interference message information in the message information, and acquiring target message information based on the removed residual message information; the interference message information is message information with the association degree with the message receiving end smaller than a preset threshold value;
inputting the target message information into a trained message sorting model, and determining a target message receiving end corresponding to the message to be distributed by the message sorting model based on the target message information;
and sending the message to be distributed to the target message receiving end.
The message distribution method, the device, the computer equipment, the storage medium and the computer program product can acquire a plurality of message information in the message to be distributed after the message distribution end receives the message to be distributed sent to the message distribution end by the message sending end, reject the interference message information in the message information, and acquire target message information based on the message information remained after the rejection, wherein the interference message information is the message information with the association degree with the message receiving end smaller than a preset threshold value; and then, the target message information can be input into a trained message sorting model, and the message sorting model determines a target message receiving end corresponding to the message to be distributed based on the target message information, so that the message to be distributed can be sent to the target message receiving end. In the method, after the interference message information in the message to be distributed is removed, the interference message information is input into the message sorting model, and the corresponding target message receiving end is determined by the model, so that the message receiving end can be determined by utilizing the analysis of the message sorting model, manual sorting is avoided, and on the other hand, the classification difficulty of the message sorting model is reduced by removing the interference information irrelevant to the determined receiving end, and the message distribution efficiency can be effectively improved.
Drawings
FIG. 1 is an application environment diagram of a message distribution method in one embodiment;
FIG. 2 is a flow chart of a method for distributing messages according to an embodiment;
FIG. 3 is a flowchart illustrating steps for determining interference message information in one embodiment;
FIG. 4 is a flow chart illustrating steps for determining interference business elements in one embodiment;
FIG. 5 is a schematic diagram of a message processing apparatus according to an embodiment;
FIG. 6 is a block diagram of a message distribution device according to one embodiment;
FIG. 7 is an internal block diagram of a computer device in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
It should be noted that the method and apparatus for distributing a message of the present application may be used in the related process of the distribution of a message in the financial field, and may also be used in the related process of the distribution of a message in any field other than the financial field, and the application fields of the method, apparatus, computer device, storage medium and computer program product for distributing a message of the present application are not limited.
The message distribution method provided by the embodiment of the application can be applied to an application environment shown in fig. 1, wherein the application environment can comprise a message sending end, a message distribution end and a message receiving end, the message sending end and the message distribution end can communicate through a network, and the message distribution end can also communicate with the message receiving end through the network.
In the application, the message distribution terminal can receive a message to be distributed, which is sent by the message sending terminal to the message distribution terminal, can acquire a plurality of message information in the message to be distributed, eliminates interference message information in the message information, and obtains target message information based on the message information remained after elimination; the interference message information is message information with the association degree with the message receiving end smaller than a preset threshold value; the message distribution end can input message information of the target message item into a trained message sorting model, and the message sorting model determines a target message receiving end corresponding to the message to be distributed based on the message information, and the message distribution end can send the message to be distributed to the target message receiving end.
The message sending end and the message distributing end can be realized by independent servers or a server cluster formed by a plurality of servers; the message sending end and the message distributing end can be provided with a data storage system, the data storage system can store data to be processed by the message distributing end, for example, a message to be forwarded to the message receiving end and a message to be distributed to the message receiving end can be stored in the data storage system of the message distributing end; the data storage system can be integrated on a message distribution end, and can also be placed on a cloud or other network servers.
The message receiving end can be a terminal, which can be, but is not limited to, various personal computers, notebook computers, tablet computers, internet of things devices and the like; of course, the message receiving end can also be implemented by an independent server or a server cluster formed by a plurality of servers.
In an alternative embodiment, the message distributing end may be a service node with the highest level among a plurality of service nodes in the service area, and the message receiving end may be a service node except the message distributing end in the service area; for example, if the service area is divided by using the province as a unit, the message distribution end may be a province service network point, and the message receiving end may be each city service network point and/or service network points below the city.
In one embodiment, as shown in fig. 2, a method for distributing a message is provided, which is illustrated by taking an example that the method is applied to the message distribution terminal in fig. 1, and may include the following steps:
s201, receiving a message to be distributed, which is sent by a message sending terminal to a message distributing terminal.
In a specific implementation, after the message receiving end obtains the message aimed at the designated message receiving end, the message can be sent to the message distributing end, and then the message distributing end can take the message from the message sending end as the message to be distributed. The number of messages sent to the message receiving end by the message sending end each time may be one or more (i.e. two or more).
S202, acquiring a plurality of message information in a message to be distributed, removing interference message information in the message information, and obtaining target message information based on the removed residual message information; the interference message information is message information with the association degree with the message receiving end smaller than a preset threshold value.
As an example, the association degree between the interference message information and the message receiving end may be understood as the degree of one-to-one correspondence between the interference message information and the message receiving end, and in practical application, part of the message information may be used to identify the corresponding message receiving end of the message to be distributed or may be used to assist in determining the corresponding message receiving end of the message to be distributed, where the higher the association degree between the message information and the message receiving end is, the higher the correspondence between the message information and the message receiving end may be. In some alternative embodiments, when the preset threshold is zero, the interference message information is irrelevant message information, and no corresponding relation exists between the irrelevant message information and the message receiving end, which can be understood as message information irrelevant to determining a specific message receiving end.
Specifically, after the message to be distributed is obtained, the message distribution terminal can analyze the message to be distributed to obtain a plurality of message information in the message to be distributed, then, the interference message information in the message information can be determined, the interference message information in the message information is removed, and the remaining message information after removal is used as target message information.
S203, inputting the target message information into a trained message sorting model, and determining a target message receiving end corresponding to the message to be distributed by the message sorting model based on the target message information.
The message sorting model can be used for determining a message receiving end of a message.
In this step, the target message information of the message to be distributed may be input into a trained message sorting model, the message sorting model performs feature extraction on the target message information, and text classification is performed based on the feature extraction result, so as to determine a message receiving end corresponding to the message to be distributed as the target message receiving end.
S204, sending the message to be distributed to the target message receiving end.
After the message distribution terminal determines the target message receiving terminal of the message to be distributed, the message distribution terminal can send the message to be distributed to the target message receiving terminal.
In this embodiment, after receiving a message to be distributed sent from a message sending end to a message distributing end, a message distributing end may obtain a plurality of message information in the message to be distributed, reject interference message information in the plurality of message information, and obtain target message information based on the message information remaining after rejection, where the interference message information is message information with a degree of association with a message receiving end smaller than a preset threshold; and then, the target message information can be input into a trained message sorting model, and the message sorting model determines a target message receiving end corresponding to the message to be distributed based on the target message information, so that the message to be distributed can be sent to the target message receiving end. In the method, after the interference message information in the message to be distributed is removed, the interference message information is input into the message sorting model, and the corresponding target message receiving end is determined by the model, so that the message receiving end can be determined by utilizing the analysis of the message sorting model, manual sorting is avoided, and on the other hand, the classification difficulty of the message sorting model is reduced by removing the interference information irrelevant to the determined receiving end, and the message distribution efficiency can be effectively improved.
In one embodiment, as shown in fig. 3, before rejecting the interference message information in the plurality of message information, the method may further include the following steps:
s301, obtaining the service type of the message to be distributed and a plurality of service elements associated with the service type.
As an example, a service element may also be called a report Wen Xiang (FIELD), which is a plurality of information related to a service in a processing procedure corresponding to a service type, and the service element may be associated with a service object (such as a message receiving end) of the processing service, a processing manner, or a processing result.
In practical applications, the plurality of messages may be messages for different service types, and in an example, the plurality of service types of the messages may be obtained according to a service type of a financial service, such as a foreign exchange transaction, a money transfer, and the like. Accordingly, since there is a difference between services of different service types, each service may have a corresponding service element, and the service elements associated with each service type may be stored in advance.
After obtaining the message to be distributed, the service type of the message to be distributed may be obtained, and in an alternative embodiment, the message receiving end may determine the service type according to the service type identifier carried by the message to be distributed, for example, the message to be distributed may carry service type identifiers such as MT100, MT201, and the like.
Further, when the service type of the message to be distributed is determined, the service element associated with the service type of the message to be distributed can be determined according to the pre-stored service elements associated with the service types.
S302, determining interference business elements with association degree with a message receiving end smaller than a preset threshold value in a plurality of business elements.
The association degree between the service element and the message receiving end can be understood as the degree of one-to-one correspondence between the service element and the message receiving end.
Specifically, among the multiple service elements of the message to be distributed, there may be information related to the message receiving end that receives the message, or there may be information related to the processing mode or the processing result; in the information related to the processing mode or the processing result, there may be information with low or no association degree with the message receiving end. Based on the above, after determining a plurality of service elements associated with the message to be distributed, an interference service element with association degree with the message receiving end smaller than a preset threshold value can be determined from the plurality of service elements.
S303, according to the interference business elements, determining interference message information in the message information.
After the interference business element is determined, the interference message information in the message information of the message to be distributed is determined based on the interference business element. Specifically, the message information under the interference service element may be determined as interference message information, for example, for message items FIELD 32 and FIELD 71 of the MT100 message, where FIELD 32 is used to record information such as information about day of rest, currency, amount, etc., FIELD 71 is used to record cost burden, and association with the message receiving end is weak; for the message items FIELD19, FIELD 30, and FIELD 32 of the MT201 message, the FIELD19 records the position total, the FIELD 30 records information such as date of interest, currency, and amount of money, and the FIELD 32 records information such as date of interest
In this embodiment, two dimensions of a service type and a service element of a message to be distributed can be combined, so that interference message information with weak relevance to a message receiving end can be quickly screened out from a plurality of message information of the message to be distributed, which is beneficial to quickly eliminating content irrelevant to message sorting in the message to be distributed and improving sorting efficiency of a message sorting model.
In one embodiment, as shown in fig. 4, S302, determining an interference service element with a degree of association with a message receiving end smaller than a preset threshold from a plurality of service elements may include the following steps:
s401, acquiring a pre-stored configuration table; the configuration table is recorded with a plurality of candidate business elements, and the association degree between each candidate business element and the message receiving end is smaller than a preset threshold value.
In a specific implementation, a configuration table may be stored in advance, where a plurality of candidate service elements are recorded in the configuration table, where the candidate service elements are service elements with a degree of association with a message receiving end smaller than a preset threshold.
In an embodiment, the plurality of candidate service elements recorded in the configuration table may be set and maintained by related service personnel, and of course, in other embodiments, the candidate service elements may also be determined according to a sorting result of the message sorting model, for example, for a message with a wrong sorting model, a service element common to the plurality of messages with the wrong sorting may be determined, and the candidate service elements are further identified according to the common service element.
S402, determining interference business elements in the business elements based on matching results of the business elements and candidate business elements in the configuration table.
After the configuration table is obtained, a plurality of service elements of the message to be distributed can be matched with each candidate service element in the configuration table one by one, if the current service element is matched with any candidate service element in the configuration table, the current service element can be determined as an interference service element, otherwise, the current service element can be ignored, and the next service element can be used as the current service element and is continuously matched with the candidate service element in the configuration table until each service element in the message to be distributed is processed, so that the interference service element in the plurality of service elements can be determined.
In this embodiment, by matching the configuration table stored in advance with each service element of the message to be distributed, the interference service element in the plurality of service elements can be rapidly determined.
In one embodiment, before rejecting the interference message information in the plurality of message information, the method may further include the steps of:
acquiring a plurality of message blocks of a message to be distributed; determining an interference message block in the message blocks, and determining message information in the interference message block as interference message information.
Wherein, the message blocks correspond to different topics; the association degree of the topic of the interference message block and the message receiving end is smaller than a preset threshold, and the association degree of the topic and the message receiving end can be understood as the one-to-one correspondence degree of the content under the topic and the message receiving end.
In a specific implementation, the message information in the message to be distributed can be divided into different message blocks, and each message block can record the content corresponding to different topics. For example, a message block corresponding to a message header may record a port number corresponding to a source port of a message sending end; the service elements of the message can be recorded in the partial message block, namely, the theme of the partial message is each service element of the message.
After obtaining the message to be distributed, a plurality of message blocks of the message to be distributed can be obtained, and the theme of each message block can be determined, for example, the theme of the message block can be determined through a pre-trained text recognition model, the sequence of each theme in the message can be predetermined, and then the theme corresponding to each message block can be obtained according to the sequence of each message block in the message.
After determining the subject of each message block, determining an interference message block from a plurality of message blocks, and determining each message information in the interference message block as interference message information. For example, for the message BLOCK 5 (trailer) of the MT100 message and the MT201 message, it may be determined as interference message information.
In this embodiment, the interference message information in the message may be quickly determined from the dimension of the message block.
In one embodiment, before receiving the message to be distributed, which is sent by the message sending end to the message distributing end, the method further comprises the following steps:
receiving messages uploaded by a plurality of message receiving terminals; encrypting the messages uploaded by the message receiving ends based on a preset appointed encryption key to obtain an encrypted message set; the method comprises the steps of sending an encrypted message set to a message sending end to trigger a message receiving end to return a plurality of messages to be distributed to a message distributing end according to the messages in the encrypted message set.
The agreed encryption key is an encryption key agreed in advance between the message distribution terminal and the message sending terminal, and the message sending terminal can be provided with an agreed decryption key corresponding to the agreed encryption key.
In practical application, the message distribution end may receive messages uploaded by multiple message receiving ends, and in one embodiment, when the message receiving end is a service node in a service area, the message receiving end may receive messages uploaded by other service nodes (i.e., multiple message receiving ends) belonging to the same service area.
After obtaining a plurality of messages from a plurality of message receiving ends, the message distribution end can obtain a preset appointed encryption key, encrypt the messages uploaded by the plurality of message receiving ends by using the appointed encryption key to obtain an encrypted message set, and can send the encrypted message set to the message sending end.
After receiving the encrypted message set, the message sending end can decrypt the encrypted message set by utilizing a preset appointed decryption key, and then the message sending end can respond to the messages in the message set and return a plurality of messages to be distributed to the message distributing end so as to send the corresponding messages to the corresponding message receiving end through the message distributing end. In an alternative embodiment, encryption can be performed between the message distribution end and the message receiving end through a DES algorithm, and encryption processing is performed on the obtained message set after the multiple messages are packaged.
In this embodiment, the message distributing end encrypts the messages uploaded from the multiple message receiving ends by using the agreed encryption key, so that the security of the packaged message set when the packaged message set is transmitted to the message sending end can be ensured.
In one embodiment, encrypting the messages uploaded by the multiple message receiving ends based on a preset agreed encryption key to obtain an encrypted message set may include the following steps:
encrypting the message uploaded by each message receiving end based on the encryption key corresponding to each message receiving end to obtain a plurality of encrypted messages; and encrypting the plurality of encrypted messages based on a preset appointed encryption key to obtain an encrypted message set.
In a specific implementation, the message distribution end and each message receiving end can determine the corresponding encryption key and decryption key in advance, and for the message uploaded by each message receiving end, the message distribution end can encrypt the message uploaded by the message receiving end based on the encryption key corresponding to the message receiving end to obtain an encrypted message, and the encrypted message can be decrypted by a device (such as the message receiving end or other authorized devices) with the decryption key, so that leakage of the message content can be avoided. In an alternative embodiment, the message uploaded by each message receiving end may be encrypted by a RSA (RSA algorithm) encryption algorithm.
When a plurality of encrypted messages are obtained, the message distribution terminal can encrypt the plurality of encrypted messages based on a preset appointed encryption key to obtain an encrypted message set.
In this embodiment, the encryption key corresponding to the message receiving end is used to encrypt a single message, so that the security of the message itself can be ensured, and the agreed encryption key is used to encrypt the files after the multiple messages are packaged, so that the security of the whole message set is ensured, and excellent effects can be achieved in both the encryption speed and the system security.
In one embodiment, the message sorting model may be trained by:
s1, eliminating interference message information in each message aiming at each message uploaded by a plurality of message receiving ends to obtain a plurality of sample messages.
In a specific implementation, after the message distribution terminal acquires the messages uploaded by the message receiving terminals, the message distribution terminal can reject the interference message information in each uploaded message, and determine each message with the interference message information rejected as a sample message, so that a plurality of sample messages can be obtained.
S2, determining a receiving end label of each sample message based on the message receiving end corresponding to each message.
After receiving each message uploaded by the message receiving end, the message distributing end can clearly know the message receiving end for transmitting each message, namely, the specific source of each message can be determined, so that the message receiving end corresponding to each message can be determined as a receiving end label.
S3, training a text classification model based on the plurality of sample messages and the receiving end label of each sample message in the plurality of sample messages, and obtaining the trained message sorting model under the condition that the training ending condition is met.
After obtaining a plurality of sample messages and the receiving end labels of each sample message, the text classification model to be trained can be trained. In an alternative embodiment, the text classification model may employ a Fastext algorithm. Fasttext is a fast text classification algorithm, its model architecture is similar to CBOWT in word2vec, except that Fasttext predicts labels (e.g., can predict specific message receiving ends) and CBOW predicts middlewords.
In the Fasttext algorithm, x can be chosen 1 ,x 2 ,...,x N-1 ,x N Input to the hidden layer of the Fasttext model, and obtain a prediction result based on the output result of the hidden layer, wherein x 1 ,x 2 ,...,x N-1 ,x N Representing an n-gram vector in a text, each feature is an average of word vectors. In practical application, after receiving the message with the interference message information removed, the Fastext algorithm may adopt an N-gram algorithm based on a language model, and perform window sliding operation with the size of N on the text content of the message according to the byte order, so as to finally form a byte fragment sequence with the window of N. Advantages of using this approach include: 1. generating better word vectors for rare words in the message; 2. even if the words in the message do not appear in the training corpus, word vectors of the words can still be constructed from the character-level n-gram; 3. the model may be allowed to learn partial information of the partial word order.
In some alternative embodiments, fasttext uses a layered softmax function, which is found on the neural networkThe output layer acts as an activation function with the purpose of normalizing the value of the output layer (output). For example, for the current message to be distributed, the A-branch prediction result z 1 =3, b-branch prediction result z 2 =1, c-branch prediction result z 3 = -3, then normalization is performed using softmax. Specifically, firstly, the prediction result may be converted into a non-negative number, and for the three prediction results, the following calculation may be performed respectively to obtain corresponding conversion results X1, X2 and X3:
X1＝exp(z 1 )＝exp(3)＝20
X2＝exp(z 2 )＝exp(1)＝2.7
X3＝exp(z 3 )＝exp(-3)＝0.05
then, the sum of the probabilities of the various predictions can be made equal to 1, namely:
Y1＝20/(20+2.7+0.05)≈0.88
Y2＝2.7/(20+2.7+0.05)≈0.12
Y3＝0.05/(20+2.7+0.05)≈0
therefore, the probability that the currently input message belongs to the A branch, the B branch or the C branch can be obtained according to Y1, Y2 and Y3.
In some embodiments, to optimize the efficiency of the standard softmax when normalized, the complexity may be reduced from N to log N by constructing a Huffman tree from the hierarchical softmax:
in the huffman tree model, the words of the leaf nodes do not have vectors that are directly output, but rather the leaf nodes all have corresponding outputs. A Huffman tree is constructed by Huffman coding, and vectors are assigned to non-leaf nodes. The probability of the target word W to be calculated can be expressed as:
p(w)＝∏σ(sign(w,j)·θ n(w,j) T h)
Wherein θn (w, j) is a vector representation of the non-leaf node n (w, j); h is the output value of the hidden layer, calculated from the vector of the input word; sign (x, j) is a special function definition. Meanwhile, the sum of probabilities of all words is 1, namely:
in some cases, as the corpus increases, the memory requirement increases, affecting the model processing speed, and there may be several solutions to this problem: 1. filtering out words with fewer occurrence times; 2. using a hash storage; 3. the word granularity is changed to be the word granularity.
In the process of training a text classification model, the training round number epoch is increased from 5 to 30, so that the learning rate h (namely the step length of gradient descent is increased) can be increased, the learning rate h is enabled to be closer to the optimal point under the limited iteration steps, in addition, 2-gram features can be added, the model is helped to capture the association between front and rear words in a message, and classification rules are better extracted for model classification.
In an embodiment, the parameter loss in the train_supported method may be set to modify the loss calculation mode (equivalent to the structure of the output layer), in an example, a softmax layer structure may be set, for example, as follows: model=fasttet.train_exceeded (input= \ "jsp.train\", lr=1.0, epoch=30, wordngrams=2, loss= 'hs'). In addition, model parameters may be related to each other, and super parameters required by different data sets are different, so that manual adjustment and searching of the super parameters become difficult, and for this, automatic super parameter adjustment may be performed by using an autotuneValidationFile parameter of fasttext, where a parameter of "autotuneValidationFile" may specify a verification data set path 'jsp.valid', it will determine a possibly optimal super parameter on a verification set by using a random search method, and when determining the optimal super parameter, the time of random search may be controlled by the autotuneDuration parameter, and may be prolonged or shortened according to different requirements, and in some examples, the random search time of 600s may be selected, that is, set to: model=fasttet.train_exceeded (input= 'jsp.train', autotunevalidly file= 'jsp.valid', autotuneduration=600).
In addition, for the multi-label multi-classification problem, since a plurality of receiving end labels are set, and softmax generally only maximizes one label, an independent classifier can be used as an output layer structure for each receiving end label, a corresponding loss calculation mode is 'ova' to represent one vs all, and the change characterization of the output layer can train a plurality of two-classification models simultaneously under unified corpus.
In this embodiment, by using the messages uploaded by the multiple message receiving ends, a large amount of corpus for training the message sorting model can be quickly obtained, and a basis is provided for subsequently improving the message sorting efficiency.
In order to enable those skilled in the art to better understand the above steps, the embodiments of the present application will be exemplified below by way of an example, but it should be understood that the embodiments of the present application are not limited thereto.
Fig. 5 shows a schematic structural diagram of a message processing device, where the device is disposed at a message receiving end, and may include: the system comprises a message sending task module, a message control module, a message sending module, a message sorting module and a task receiving module.
And the information sending task module is used for sending information: the message to be distributed can be obtained from a financial institution business system (a message sending end), and can be stored into a message sending text for sending in a preset format; in addition, the message to be printed can be processed by the message sending task module. Preferably, but not limited to, establishing a communication connection with a financial institution business system through an MQ (message queue) to effect message interaction. Specifically, communication connection can be established between the local message queue MQ corresponding to the financial institution service system and the local queue manager in the local MQ of the message distribution end, and between the target queue managers of the target MQ corresponding to the SWIFT terminal system in the local MQ of the message distribution end, and SWIFT messages to be received can be obtained from the receiving queues of the designated local queue manager according to the MQ configuration information.
Message control module: the message uploaded by the financial institution business system can be normalized according to the requirement of a SWIFT terminal (such as PCC) (for example, the length of the message is 512 bytes, and the suffix name is ABI); and meanwhile, preprocessing the messages uploaded by the financial institution business system, and generating training data for training a message sorting model. The message control module can also monitor each processing link of the message for inquiry and backup the message files of some important links. In addition, the message control module may split the file issued from the PCC, convert the service requirement of the incoming message of the PCC, issue the converted message to the service system of the financial institution, and record the received message Wen Huizhi (ACK, NAK, UNK).
And a message sending module: multiple messages can be packaged into one file and sent to the PCC. In an alternative embodiment, the encrypted transmission of data may be achieved by a combination of two encryption techniques at the same time: adopting RSA algorithm for providing data signature, identity authentication and the like, and encrypting a single message by combining the RSA algorithm to ensure the safety of the message; and the transmission data between PCCs can be encrypted by adopting a DES algorithm, namely, the files packaged by a plurality of messages uploaded by the business systems of all financial institutions are encrypted, so that the security of the whole file package is ensured. Thereby achieving better effects in both encryption speed and system security. In addition, the generated but not sent message can be deleted; inquiring and counting the sent and deleted messages; unreleasase operation is performed on a message (an operation that allows manual intervention to be intercepted and not sent out before the message is sent out).
And a report task module: the deploying watch mechanism realizes the interaction of the files on the appointed storage service and acquires the report files of the PCC system. In an alternative embodiment, two encryption technologies can be combined to realize encryption transmission of data, RSA algorithm is adopted in the aspects of data signature provision, identity authentication and the like, and DES algorithm is adopted to encrypt transmission data, so that good effects are achieved in the aspects of encryption speed and system security.
Message sorting module: splitting incoming message files of the PCC system one by one, eliminating interference information in the messages according to predefined rules, and determining a target message receiving end of each message through sorting model matching after preprocessing is completed. After matching is completed, the messages belonging to each branch are sent to a financial institution business system through the MQ. In addition, the incorrectly allocated messages can be re-sorted.
By the message processing equipment, the automation degree of message processing can be improved, risks can be reduced, efficiency can be improved, processing capacity can be improved, and sorting accuracy can be improved.
It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.
Based on the same inventive concept, the embodiment of the application also provides a message distribution device for realizing the above related message distribution method. The implementation of the solution provided by the device is similar to the implementation described in the above method, so the specific limitation of one or more embodiments of the message distribution device provided below may refer to the limitation of the message distribution method hereinabove, and will not be repeated herein.
In one embodiment, as shown in fig. 6, there is provided a message distribution apparatus, including:
the message receiving module 601 is configured to receive a message to be distributed, which is sent by a message sending end to a message distributing end;
an interference message information removing module 602, configured to obtain a plurality of message information in the message to be distributed, remove the interference message information in the plurality of message information, and obtain target message information based on the remaining message information after removal; the interference message information is message information with the association degree with the message receiving end smaller than a preset threshold value;
the sorting module 603 is configured to input the target message information into a trained message sorting model, and determine, by the message sorting model, a target message receiving end corresponding to the message to be distributed based on the target message information;
And the message forwarding module 604 is configured to send the message to be distributed to the target message receiving end.
In one embodiment, the interfering message information rejection module 602 is further configured to:
acquiring a service type of the message to be distributed and a plurality of service elements associated with the service type;
determining interference business elements of which the association degree with a message receiving end is smaller than a preset threshold value in the business elements;
and determining the interference message information in the message information according to the interference service element.
In one embodiment, the interference message information rejection module 602 is specifically configured to:
acquiring a pre-stored configuration table; the configuration table is recorded with a plurality of candidate business elements, and the association degree between each candidate business element and the message receiving end is smaller than a preset threshold value;
and determining interference business elements in the business elements based on the matching result of the business elements and each candidate business element in the configuration table.
In one embodiment, the interfering message information rejection module 602 is further configured to:
acquiring a plurality of message blocks of the message to be distributed; the message blocks correspond to different topics;
Determining an interference message block in the message blocks, and determining message information in the interference message block as interference message information; and the association degree between the subject of the interference message block and the message receiving end is smaller than a preset threshold value.
In one embodiment, the apparatus further comprises:
the uploading message acquisition module is used for receiving messages uploaded by a plurality of message receiving ends;
the encryption module is used for encrypting the messages uploaded by the message receiving ends based on a preset appointed encryption key to obtain an encrypted message set; the agreed encryption key is an encryption key agreed in advance between the message distribution terminal and the message transmission terminal;
and the encrypted message sending module is used for sending the encrypted message set to the message sending end so as to trigger the message sending end to return a plurality of messages to be distributed to the message distributing end according to the messages in the encrypted message set.
In one embodiment, the encryption module is configured to:
encrypting the message uploaded by each message receiving end based on the encryption key corresponding to each message receiving end to obtain a plurality of encrypted messages;
encrypting the plurality of encrypted messages based on a preset appointed encryption key to obtain an encrypted message set.
In one embodiment, the message sorting model is trained by:
for each message uploaded by the message receiving terminals, rejecting the interference message information in each message to obtain a plurality of sample messages;
determining a receiving end label of each sample message based on the message receiving end corresponding to each message;
training a text classification model based on the plurality of sample messages and the receiving end labels of each sample message in the plurality of sample messages, and obtaining the trained message sorting model under the condition that training ending conditions are met.
The modules in the message distribution device can be implemented in whole or in part by software, hardware and a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 7. The computer device includes a processor, a memory, an Input/Output interface (I/O) and a communication interface. The processor, the memory and the input/output interface are connected through a system bus, and the communication interface is connected to the system bus through the input/output interface. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used for storing message data. The input/output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a method of message distribution.
It will be appreciated by those skilled in the art that the structure shown in fig. 7 is merely a block diagram of some of the structures associated with the present application and is not limiting of the computer device to which the present application may be applied, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided comprising a memory and a processor, the memory having stored therein a computer program, the processor when executing the computer program performing the steps of:
a receiving message sending end sends a message to be distributed to a message distributing end;
acquiring a plurality of message information in the message to be distributed, removing interference message information in the message information, and acquiring target message information based on the removed residual message information; the interference message information is message information with the association degree with the message receiving end smaller than a preset threshold value;
inputting the target message information into a trained message sorting model, and determining a target message receiving end corresponding to the message to be distributed by the message sorting model based on the target message information;
And sending the message to be distributed to the target message receiving end.
In one embodiment, the steps of the other embodiments described above are also implemented when the processor executes a computer program.
In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of:
a receiving message sending end sends a message to be distributed to a message distributing end;
acquiring a plurality of message information in the message to be distributed, removing interference message information in the message information, and acquiring target message information based on the removed residual message information; the interference message information is message information with the association degree with the message receiving end smaller than a preset threshold value;
inputting the target message information into a trained message sorting model, and determining a target message receiving end corresponding to the message to be distributed by the message sorting model based on the target message information;
and sending the message to be distributed to the target message receiving end.
In one embodiment, the computer program, when executed by a processor, also implements the steps of the other embodiments described above.
In one embodiment, a computer program product is provided comprising a computer program which, when executed by a processor, performs the steps of:
A receiving message sending end sends a message to be distributed to a message distributing end;
acquiring a plurality of message information in the message to be distributed, removing interference message information in the message information, and acquiring target message information based on the removed residual message information; the interference message information is message information with the association degree with the message receiving end smaller than a preset threshold value;
inputting the target message information into a trained message sorting model, and determining a target message receiving end corresponding to the message to be distributed by the message sorting model based on the target message information;
and sending the message to be distributed to the target message receiving end.
In one embodiment, the computer program, when executed by a processor, also implements the steps of the other embodiments described above.
It should be noted that, the user information (including, but not limited to, user equipment information, user personal information, etc.) and the data (including, but not limited to, data for analysis, stored data, presented data, etc.) referred to in the present application are information and data authorized by the user or sufficiently authorized by each party, and the collection, use and processing of the related data are required to comply with the related laws and regulations and standards of the related countries and regions.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the various embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the various embodiments provided herein may include at least one of relational databases and non-relational databases. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic units, quantum computing-based data processing logic units, etc., without being limited thereto.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples only represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the present application. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application shall be subject to the appended claims.
Claims (11)
1. A method for distributing messages, the method comprising:
a receiving message sending end sends a message to be distributed to a message distributing end;
acquiring a plurality of message information in the message to be distributed, removing interference message information in the message information, and acquiring target message information based on the removed residual message information; the interference message information is message information with the association degree with the message receiving end smaller than a preset threshold value;
Inputting the target message information into a trained message sorting model, and determining a target message receiving end corresponding to the message to be distributed by the message sorting model based on the target message information;
and sending the message to be distributed to the target message receiving end.
2. The method of claim 1, further comprising, prior to said rejecting the interfering message information in the plurality of message information:
acquiring a service type of the message to be distributed and a plurality of service elements associated with the service type;
determining interference business elements of which the association degree with a message receiving end is smaller than a preset threshold value in the business elements;
and determining the interference message information in the message information according to the interference service element.
3. The method of claim 2, wherein the determining, of the plurality of service elements, an interference service element having a degree of association with the message receiving end less than a preset threshold comprises:
acquiring a pre-stored configuration table; the configuration table is recorded with a plurality of candidate business elements, and the association degree between each candidate business element and the message receiving end is smaller than a preset threshold value;
And determining interference business elements in the business elements based on the matching result of the business elements and each candidate business element in the configuration table.
4. The method of claim 1, further comprising, prior to said rejecting the interfering message information in the plurality of message information:
acquiring a plurality of message blocks of the message to be distributed; the message blocks correspond to different topics;
determining an interference message block in the message blocks, and determining message information in the interference message block as interference message information; and the association degree between the subject of the interference message block and the message receiving end is smaller than a preset threshold value.
5. The method according to any one of claims 1-4, further comprising, before the receiving the message sent by the message sending end to the message distributing end,:
receiving messages uploaded by a plurality of message receiving terminals;
encrypting the messages uploaded by the message receiving ends based on a preset appointed encryption key to obtain an encrypted message set; the agreed encryption key is an encryption key agreed in advance between the message distribution terminal and the message transmission terminal;
And sending the encrypted message set to the message sending end so as to trigger the message sending end to return a plurality of messages to be distributed to the message distributing end according to the messages in the encrypted message set.
6. The method according to claim 5, wherein encrypting the messages uploaded by the plurality of message receiving terminals based on the preset agreed encryption key to obtain the encrypted message set comprises:
encrypting the message uploaded by each message receiving end based on the encryption key corresponding to each message receiving end to obtain a plurality of encrypted messages;
encrypting the plurality of encrypted messages based on a preset appointed encryption key to obtain an encrypted message set.
7. The method of claim 5, wherein the message sorting model is trained by:
for each message uploaded by the message receiving terminals, rejecting the interference message information in each message to obtain a plurality of sample messages;
determining a receiving end label of each sample message based on the message receiving end corresponding to each message;
training a text classification model based on the plurality of sample messages and the receiving end labels of each sample message in the plurality of sample messages, and obtaining the trained message sorting model under the condition that training ending conditions are met.
8. A message distribution apparatus, the apparatus comprising:
the message receiving module is used for receiving a message to be distributed, which is sent to the message distribution terminal by the message sending terminal;
the interference message information eliminating module is used for acquiring a plurality of message information in the message to be distributed, eliminating the interference message information in the message information and obtaining target message information based on the residual message information after elimination; the interference message information is message information with the association degree with the message receiving end smaller than a preset threshold value;
the sorting module is used for inputting the target message information into a trained message sorting model, and determining a target message receiving end corresponding to the message to be distributed based on the target message information by the message sorting model;
and the message forwarding module is used for sending the message to be distributed to the target message receiving end.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 7 when the computer program is executed.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 7.
11. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310268123.2A CN116318549A (en) | 2023-03-17 | 2023-03-17 | Message distribution method, device, computer equipment, storage medium and product |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310268123.2A CN116318549A (en) | 2023-03-17 | 2023-03-17 | Message distribution method, device, computer equipment, storage medium and product |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116318549A true CN116318549A (en) | 2023-06-23 |
Family
ID=86786659
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310268123.2A Pending CN116318549A (en) | 2023-03-17 | 2023-03-17 | Message distribution method, device, computer equipment, storage medium and product |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116318549A (en) |
-
2023
- 2023-03-17 CN CN202310268123.2A patent/CN116318549A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Akgun et al. | A new DDoS attacks intrusion detection model based on deep learning for cybersecurity | |
| Alam et al. | Processing social media images by combining human and machine computing during crises | |
| US20220230071A1 (en) | Method and device for constructing decision tree | |
| CN110457912B (en) | Data processing method and device and electronic equipment | |
| US11151660B1 (en) | Intelligent routing control | |
| CN111784001B (en) | Model training method and device and computer readable storage medium | |
| Hu et al. | Federated learning: a distributed shared machine learning method | |
| CN112529101B (en) | Classification model training method and device, electronic equipment and storage medium | |
| CN111144576A (en) | Model training method and device and electronic equipment | |
| Zheng et al. | GCN‐ETA: High‐Efficiency Encrypted Malicious Traffic Detection | |
| Yang et al. | Malicious encryption traffic detection based on NLP | |
| de Mello et al. | Identifying Encryption Algorithms in ECB and CBC Modes Using Computational Intelligence. | |
| CN111680161A (en) | Text processing method and device and computer readable storage medium | |
| Kim et al. | Threat classification model for security information event management focusing on model efficiency | |
| Long et al. | Deep encrypted traffic detection: An anomaly detection framework for encryption traffic based on parallel automatic feature extraction | |
| US20220050825A1 (en) | Block chain based management of auto regressive database relationships | |
| Zheng et al. | An efficient multikeyword fuzzy ciphertext retrieval scheme based on distributed transmission for Internet of Things | |
| US20240111892A1 (en) | Systems and methods for facilitating on-demand artificial intelligence models for sanitizing sensitive data | |
| US20240111891A1 (en) | Systems and methods for sanitizing sensitive data and preventing data leakage using on-demand artificial intelligence models | |
| Peng et al. | Federated meta embedding concept stock recommendation | |
| CN116318549A (en) | Message distribution method, device, computer equipment, storage medium and product | |
| Baligodugula et al. | A Comparative Study of Secure and Efficient Data Duplication Mechanisms for Cloud-Based IoT Applications | |
| Wang et al. | Multiple Differential Distinguisher of SIMECK32/64 Based on Deep Learning | |
| Zhang et al. | Detection Method of Illegal Registered Account Behavior Based on GNN | |
| US11698977B1 (en) | Predicting and quantifying weaponization of software weaknesses |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |